• The Journal of Bigdata
• /
• v.4 no.2
• /
• pp.35-45
• /
• 2019

Recently, the damage with social cost of malicious comments is increasing. In addition to the news of talent committing suicide through the effects of malicious comments. The damage to malicious comments including abusive language and slang is increasing and spreading in various type and forms throughout society. In this paper, we propose a technique for detecting abusive language using a bi-directional long short-term memory neural network model. We collected comments on the web through the web crawler and processed the stopwords on unused words such as English Alphabet or special characters. For the stopwords processed comments, the bidirectional long short-term memory neural network model considering the front word and back word of sentences was used to determine and detect abusive language. In order to use the bi-directional long short-term memory neural network, the detected comments were subjected to morphological analysis and vectorization, and each word was labeled with abusive language. Experimental results showed a performance of 88.79% for a total of 9,288 comments screened and collected.

• Journal of Contemporary Eastern Asia
• /
• v.18 no.1
• /
• pp.189-216
• /
• 2019

The frequent occurrence of overwhelming disasters necessitates risk communication systems capable of operating effectively in disaster contexts. Few studies have examined risk communication networks during disasters through social networking services (SNS). This study therefore investigates the patterns of risk communication by comparing Korean and international networks based on the social amplification of risk communication in the context of the Sewol ferry disaster (SFD). In addition, differences in language use and patterns between Korean and international contexts are identified through a semantic analysis using KrKwick, NodeXL, and UCINET. The SFD refers to the sinking of the ferry while carrying 476 people, mostly secondary school students. The results for interpersonal risk communication reveal that the structure of the Korean risk communication network differed from that of the international network. The Korean network was more fragmented, and its clustering was more sparsely knitted based on the impact and physical proximity of the disaster. Semantic networks imply that the physical distance from the disaster affected the content of risk communication, as well as the network pattern.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.10a
• /
• pp.269-271
• /
• 2022

In recent years, RNN networks with LSTM blocks have been used extensively in machine learning tasks that process sequential data. These networks have proven to be particularly good at sequential language processing tasks by being more able to accurately predict the next most likely word in a given sequence than traditional neural networks. This study trained an RNN / LSTM neural network on three different translations of 150 biblical Psalms - in both English and Korean. The resulting model is then fed an input word and a length number from which it automatically generates a new Psalm of the desired length based on the patterns it recognized while training. The results of training the network on both English text and Korean text are compared and discussed.

• The Journal of the Korea Contents Association
• /
• v.16 no.5
• /
• pp.385-398
• /
• 2016

This research analyzed domestic newspapers' agenda setting trend and meaning construction process on the issue of marine environment by year. The research conducted a language network analysis and used R program and Netminer program to analyze four major daily newspapers' news coverages (Dong-A, Joongang, Hanhyoreh, and Kyunghyang) for the last ten years (2005-2014). The results show that the issue of marine environment in Korean media reports are signified in the economic context. For the last ten years, news reports are mainly focused on the 'development' issue of marine environment, without distinction of year. The core key words of the networks are "development", "plan", and "project." However, diverse strategies for 'preservation' are not covered in media reports as a major issue. The importance of effective preservation and reasonable development should be considered in a balanced way. Korean media coverages mainly concentrate on the development issue, and it has a strong influence on considering the marine environment area as an object of development. Future direction and implication of the press reports related to marine environment are discussed.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.15 no.4
• /
• pp.2074-2084
• /
• 2014

Social capital is an important resource for Korean immigrant children's successful school life in the U.S. because most immigrants are not familiar to new language and culture. However, immigrant parents and their children have limited ability to join and create social networks freely both inside and outside school. We, the researchers of this study, adopted qualitative research method: open-ended in-depth interview, coding and analysis based on grounded theory. The result of this study reveals that Korean immigrant parents utilize their coethnic networks in getting educational information and English plays important role in educational decision-making process of the parents.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.11 no.2
• /
• pp.901-923
• /
• 2017

Efficient key distribution and management mechanisms as well as lightweight ciphers are the main pillar for establishing secure wireless sensor networks (WSN). Several symmetric based key distribution protocols are already proposed, but most of them are not scalable, yet vulnerable to a small number of compromised nodes. In this paper, we propose an efficient and scalable key management and distribution framework, named KMMR, for large scale WSNs. The KMMR contributions are three fold. First, it performs lightweight local processes orchestrated into upward and downward tiers. Second, it limits the impact of compromised nodes to only local links. Third, KMMR performs efficient secure node addition and revocation. The security analysis shows that KMMR withstands several known attacks. We implemented KMMR using the NesC language and experimented on Telosb motes. Performance evaluation using the TOSSIM simulator shows that KMMR is scalable, provides an excellent key connectivity and allows a good resilience, yet it ensures both forward and backward secrecy. For a WSN comprising 961 sensor nodes monitoring a 60 hectares agriculture field, KMMR requires around 2.5 seconds to distribute all necessary keys, and attains a key connectivity above 96% and a resilience approaching 100%. Quantitative comparisons to earlier work show that KMMR is more efficient in terms of computational complexity, required storage space and communication overhead.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.23 no.11
• /
• pp.1321-1329
• /
• 2019

With the development of social information networks, the marketing methods are also changing in various ways. Unlike successful marketing methods based on existing celebrities and financial support, Influencer-based marketing is a big trend and very famous. In this paper, we first extract influencer features from more than 54 YouTube channels using the multi-dimensional qualitative analysis based on the meta information and comment data analysis of YouTube, model representative themes to maximize a personalized video satisfaction. Plus, the purpose of this study is to provide supplementary means for the successful promotion and marketing by creating and distributing videos of new items by referring to the existing Influencer features. For that we assume all comments of various videos for each channel as each document, TF-IDF (Term Frequency and Inverse Document Frequency) and LDA (Latent Dirichlet Allocation) algorithms are applied to maximize performance of the proposed scheme. Based on the performance evaluation, we proved the proposed scheme is better than other schemes.

• The Journal of the Korea Contents Association
• /
• v.15 no.11
• /
• pp.359-373
• /
• 2015

Cognitive reserve(CR) is the ability to optimize or maximize performance through complementary brain networks. CR is relevant to normal aging in cognitive-linguistic abilities. There are few domestic systematic reviews or meta-analyses that analyze the relationships between multiple CR and cognitive-linguistic domains in healthy older people. This meta-analysis included 32 studies published since 2000. In result, education level topped the list, followed by the occupation, cognitively stimulating activities, and the multilingualism. Most studies were related to memory, global cognition, and language. CR had a modest positive association with cognitive-linguistic performance. Multiple domains including memory and language also showed the significant correlations across most measures of CR. This study provides evidence-based information to support cognitive-linguistic ability in normal aging.

• Journal of Information Science Theory and Practice
• /
• v.10 no.spc
• /
• pp.143-153
• /
• 2022

With the development of networks and the increase in the number of network devices, the number of cyber attacks targeting them is also increasing. Since these cyber-attacks aim to steal important information and destroy systems, it is necessary to minimize social and economic damage through early detection and rapid response. Many studies using machine learning (ML) and artificial intelligence (AI) have been conducted, among which payload learning is one of the most intuitive and effective methods to detect malicious behavior. In this study, we propose a preprocessing method to maximize the performance of the model when learning the payload in term units. The proposed method constructs a high-quality learning data set by eliminating unnecessary noise (stopwords) and preserving important features in consideration of the machine language and natural language characteristics of the packet payload. Our method consists of three steps: Preserving significant special characters, Generating a stopword list, and Class label refinement. By processing packets of various and complex structures based on these three processes, it is possible to make high-quality training data that can be helpful to build high-performance ML/AI models for security monitoring. We prove the effectiveness of the proposed method by comparing the performance of the AI model to which the proposed method is applied and not. Forthermore, by evaluating the performance of the AI model applied proposed method in the real-world Security Operating Center (SOC) environment with live network traffic, we demonstrate the applicability of the our method to the real environment.

• Journal of Information Science Theory and Practice
• /
• v.12 no.2
• /
• pp.64-78
• /
• 2024

Sentiment analysis is one of the promising approaches for developing a point of interest (POI) recommendation system. It uses natural language processing techniques that deploy expert insights from user-generated content such as reviews and feedback. By applying sentiment polarities (positive, negative, or neutral) associated with each POI, the recommendation system can suggest the most suitable POIs for specific users. The proposed study combines two models for POI recommendation. The first model uses bidirectional long short-term memory (BiLSTM) to predict sentiments and is trained on an election dataset. It is observed that the proposed model outperforms existing models in terms of accuracy (99.52%), precision (99.53%), recall (99.51%), and F1-score (99.52%). Then, this model is used on the Foursquare dataset to predict the class labels. Following this, user and POI embeddings are generated. The next model recommends the top POIs and corresponding coordinates to the user using the LSTM model. Filtered user interest and locations are used to recommend POIs from the Foursquare dataset. The results of our proposed model for the POI recommendation system using sentiment analysis are compared to several state-of-the-art approaches and are found quite affirmative regarding recall (48.5%) and precision (85%). The proposed system can be used for trip advice, group recommendations, and interesting place recommendations to specific users.